knowledge-wiki-template: Skill for Claude Code

.claude/skills/knowledge-wiki-concept/SKILL.md

knowledge-wiki-concept is a skill for Claude Code from CatChen/knowledge-wiki-template. It costs 48 tokens per session (1,263 once invoked), scanned A, original, MIT.

A tool that creates or updates concept articles in a knowledge wiki from summary files. It processes summaries that are new or changed since its previous run.

In plain words
What is it for?
Use it to populate or refresh the Wiki/Concepts folder after summaries are created or updated. It extracts the listed key concepts from each summary.
Why use it?
It turns collected summaries into organized concept notes, so the wiki can be refreshed as source material changes. It avoids reprocessing summaries that have not changed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is CatChen/knowledge-wiki-template's own configuration. It tells Claude Code how to work on knowledge-wiki-template itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything knowledge-wiki-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CatChen/knowledge-wiki-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CatChen/knowledge-wiki-template/main/.claude/skills/knowledge-wiki-concept/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/CatChen/knowledge-wiki-template

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for knowledge-wiki-concept

README.md
[![agentmods](https://agentmods.dev/badge/skills/catchen/knowledge-wiki-template/knowledge-wiki-concept/github.svg)](https://agentmods.dev/skills/catchen/knowledge-wiki-template/knowledge-wiki-concept)
Your own site
<a href="https://agentmods.dev/skills/catchen/knowledge-wiki-template/knowledge-wiki-concept"><img src="https://agentmods.dev/badge/skills/catchen/knowledge-wiki-template/knowledge-wiki-concept/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for knowledge-wiki-concept

Your own site · 80×15
<a href="https://agentmods.dev/skills/catchen/knowledge-wiki-template/knowledge-wiki-concept"><img src="https://agentmods.dev/badge/skills/catchen/knowledge-wiki-template/knowledge-wiki-concept.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,263 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.01263
Opus 5.5 $0.00019 $0.00505
Sonnet 5.5 $0.00010 $0.00253
Haiku 4.5 $0.00005 $0.00126

Measured 2mo ago against content hash 572eaa600c4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

knowledge-wiki-concept scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/knowledge-wiki-concept/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Wiki Concept

Create or update concept articles in Wiki/Concepts/ by extracting concepts from summary files that have been updated since the last run.

Steps

1. Establish the working directory

The knowledge base root is the Git repository root. Run git rev-parse --show-toplevel and store the result as KNOWLEDGE_PATH.

Use KNOWLEDGE_PATH for all subsequent steps.

2. Find summary files to process

Run:

node {KNOWLEDGE_PATH}/scripts/wiki/wiki-state.mjs find-unprocessed-summaries knowledge-wiki-concept

This outputs a JSON array of summary file paths (relative to KNOWLEDGE_PATH) that are new or updated since the last run. Example:

[
  "Wiki/Summaries/Posts/Alexa, tell me a joke..summary.md",
  "Wiki/Summaries/Posts/Vision Pro 使用体验(Part 1).summary.md"
]

If the array is empty, print Nothing to process. and stop.

3. Process each summary file

For each path in the array from step 2, run the following sub-steps.


3a. Read the summary file

Read the summary file using the Read tool.

Parse the ## Key Concepts section. Each line has the form:

- [[Wiki/Concepts/{concept-slug}|{Display Name}]] — {description}

Extract the slug, display name, and description for each concept.

Also note the summary file's tags frontmatter field — you may draw on these when choosing concept tags, but only include tags that are genuinely relevant to the concept itself.

Derive the summary's link-path by stripping the .md extension from the summary file path, and store it as {summary-link-path}. Example: Wiki/Summaries/Posts/foo.summary.md → Wiki/Summaries/Posts/foo.summary


3b. For each concept, create or update its file

If the concept file does NOT exist, create it:

  1. Run:
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-concept.mjs create "{concept-slug}" "{Display Name}"
    
    This creates Wiki/Concepts/{concept-slug}.md with frontmatter and an empty ## Sources section. The command prints the file path.

Read the full file on GitHub · 126 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 126 lines · 48 tokens per session scan A 572eaa600c4e

Subscribe to this mod's changes

knowledge-wiki-concept is a skill published in the GitHub repository CatChen/knowledge-wiki-template (106 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 1,263 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

knowledge-wiki-concept compared with skills from other repositories

knowledge-wiki-concept next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
knowledge-wiki-conceptCatChen/knowledge-wiki-templateSkill1064mo agoMITA48Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143ktodayMITA103Claude Code